Inferenzführung

Details

Veröffentlichungs-Nr.

EP4722973

Anmeldetag

6. August 2025

Veröffentlichung

8. April 2026

Rechtsraum

EP

Abstract

A computer-implemented method comprising: generating, based on a plurality of candidate output tokens generated by a large language model, LLM, a plurality of candidate token embeddings, respectively and generating, based on at least one string describing prohibited content, at least one content embedding; comparing the candidate token embeddings with the at least one content embedding to determine for each candidate output token a similarity score indicating similarity between the candidate output token and the prohibited/unwanted content; for each candidate output token, generating, based on the similarity score and based on a selection probability assigned by the LLM to the candidate output token, an output score; and selecting, based on the output scores, a candidate output token for output by the LLM.

Anmelder

Firmen

FUJITSU LIMITED
B.G. Negev Technologies and Applications Ltd. at Ben-Gurion University

Land

🇯🇵 Japan